Exploiting Conic Affinity Measures to Design Speech Enhancement Systems Operating in Unseen Noise Conditions

Pavlos Papadopoulos, Shrikanth Narayanan


Speech enhancement under unseen noise conditions is a challenging task, but essential for meeting the increasing demand for speech technologies to operate in diverse and dynamic real world environments. A method that has been widely used to enhance speech signals is nonnegative matrix factorization (NMF). In the training phase NMF produces speech and noise dictionaries which are represented as matrices with nonnegative entries. The quality of the enhanced signal depends on the reconstruction ability of the dictionaries. A geometric interpretation of these nonnegative matrices enables us to cast them as convex polyhedral cones in the positive orthant. In this work, we employ conic affinity measures to design systems able to operate in unseen noise conditions, by selecting an appropriate noise dictionary amongst a pool of potential candidates. We show that such a method yields results similar to those that would be produced if the oracle noise dictionary was used.


 DOI: 10.21437/Interspeech.2020-1269

Cite as: Papadopoulos, P., Narayanan, S. (2020) Exploiting Conic Affinity Measures to Design Speech Enhancement Systems Operating in Unseen Noise Conditions. Proc. Interspeech 2020, 4029-4033, DOI: 10.21437/Interspeech.2020-1269.


@inproceedings{Papadopoulos2020,
  author={Pavlos Papadopoulos and Shrikanth Narayanan},
  title={{Exploiting Conic Affinity Measures to Design Speech Enhancement Systems Operating in Unseen Noise Conditions}},
  year=2020,
  booktitle={Proc. Interspeech 2020},
  pages={4029--4033},
  doi={10.21437/Interspeech.2020-1269},
  url={http://dx.doi.org/10.21437/Interspeech.2020-1269}
}